# Evolving Spatially Aggregated Features from Satellite Imagery for Regional Modeling

## TL;DR

This paper introduces a genetic programming-based method to automatically generate spatially aggregated features from satellite imagery, improving regional modeling of geospatial phenomena like snow properties.

## Contribution

It presents a novel approach that uses genetic programming to induce spatial aggregations driven by model performance, enhancing feature construction for regional analysis.

## Key findings

- Genetic programming effectively synthesizes relevant spatial aggregations.
- The method improves predictive accuracy over traditional regression techniques.
- Applicable to real-world geospatial datasets, such as snow property prediction.

## Abstract

Satellite imagery and remote sensing provide explanatory variables at relatively high resolutions for modeling geospatial phenomena, yet regional summaries are often desirable for analysis and actionable insight. In this paper, we propose a novel method of inducing spatial aggregations as a component of the machine learning process, yielding regional model features whose construction is driven by model prediction performance rather than prior assumptions. Our results demonstrate that Genetic Programming is particularly well suited to this type of feature construction because it can automatically synthesize appropriate aggregations, as well as better incorporate them into predictive models compared to other regression methods we tested. In our experiments we consider a specific problem instance and real-world dataset relevant to predicting snow properties in high-mountain Asia.